Worked on the ml-explore/mlx-lm repository to enhance model management by implementing flexible model sourcing capabilities. Developed a feature that enables downloading model snapshots from ModelScope, introducing environment variable toggles to seamlessly switch between ModelScope and Hugging Face Hub. This approach allows deployment pipelines to adapt sourcing strategies based on environment needs, reducing vendor lock-in and streamlining integration. The solution was built using Python and focused on backend development and API integration, with no major bugs reported during the period. The work improved deployment readiness and provided a more adaptable infrastructure for managing machine learning models across different environments.